1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
## ----loadLibs, include = FALSE-----------------------
library(MASS)
library(caret)
library(mlbench)
data(Sonar)
library(pls)
library(klaR)
library(knitr)
opts_chunk$set(
comment = "#>",
collapse = TRUE,
digits = 3,
tidy = FALSE,
background = "#FFFF00",
fig.align = 'center',
warning = FALSE,
message = FALSE
)
options(width = 55, digits = 3)
theme_set(theme_bw())
getInfo <- function(what = "Suggests") {
text <- packageDescription("caret")[what][[1]]
text <- gsub("\n", ", ", text, fixed = TRUE)
text <- gsub(">=", "$\\\\ge$", text, fixed = TRUE)
eachPkg <- strsplit(text, ", ", fixed = TRUE)[[1]]
eachPkg <- gsub(",", "", eachPkg, fixed = TRUE)
#out <- paste("\\\**", eachPkg[order(tolower(eachPkg))], "}", sep = "")
#paste(out, collapse = ", ")
length(eachPkg)
}
## ----install, eval = FALSE---------------------------
# install.packages("caret", dependencies = c("Depends", "Suggests"))
## ----SonarSplit--------------------------------------
library(caret)
library(mlbench)
data(Sonar)
set.seed(107)
inTrain <- createDataPartition(
y = Sonar$Class,
## the outcome data are needed
p = .75,
## The percentage of data in the
## training set
list = FALSE
)
## The format of the results
## The output is a set of integers for the rows of Sonar
## that belong in the training set.
str(inTrain)
## ----SonarDatasets-----------------------------------
training <- Sonar[ inTrain,]
testing <- Sonar[-inTrain,]
nrow(training)
nrow(testing)
## ----plsTune1, eval = FALSE--------------------------
# plsFit <- train(
# Class ~ .,
# data = training,
# method = "pls",
# ## Center and scale the predictors for the training
# ## set and all future samples.
# preProc = c("center", "scale")
# )
## ----pls_fit-----------------------------------------
ctrl <- trainControl(
method = "repeatedcv",
repeats = 3,
classProbs = TRUE,
summaryFunction = twoClassSummary
)
set.seed(123)
plsFit <- train(
Class ~ .,
data = training,
method = "pls",
preProc = c("center", "scale"),
tuneLength = 15,
trControl = ctrl,
metric = "ROC"
)
plsFit
## ----pls-plot----------------------------------------
ggplot(plsFit)
## ----plsPred-----------------------------------------
plsClasses <- predict(plsFit, newdata = testing)
str(plsClasses)
plsProbs <- predict(plsFit, newdata = testing, type = "prob")
head(plsProbs)
## ----plsCM-------------------------------------------
confusionMatrix(data = plsClasses, testing$Class)
## ----rdaFit------------------------------------------
## To illustrate, a custom grid is used
rdaGrid = data.frame(gamma = (0:4)/4, lambda = 3/4)
set.seed(123)
rdaFit <- train(
Class ~ .,
data = training,
method = "rda",
tuneGrid = rdaGrid,
trControl = ctrl,
metric = "ROC"
)
rdaFit
rdaClasses <- predict(rdaFit, newdata = testing)
confusionMatrix(rdaClasses, testing$Class)
## ----rs----------------------------------------------
resamps <- resamples(list(pls = plsFit, rda = rdaFit))
summary(resamps)
## ----BA----------------------------------------------
xyplot(resamps, what = "BlandAltman")
## ----diffs-------------------------------------------
diffs <- diff(resamps)
summary(diffs)
|
